© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 78137
    Prev
    Next
    INDEX
    Explanations

    terms related to political conflict and ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -widgets
    -0.07
    errupted
    -0.06
    .dk
    -0.06
    루
    -0.06
    Buzz
    -0.06
    tru
    -0.06
    InnerHTML
    -0.06
    егод
    -0.06
    askan
    -0.06
    buzz
    -0.06
    POSITIVE LOGITS
     friendly
    0.11
    friendly
    0.10
     sympathetic
    0.10
     friend
    0.09
     Friendly
    0.09
     supportive
    0.08
     allied
    0.08
     sympathy
    0.08
     allies
    0.08
     support
    0.08
    Activations Density 0.061%

    No Known Activations